ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Маскированные автокодировщики×Swin Transformer×Vision Transformer×
ОбластьГлубокое обучениеГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learningMachine learning
Год появления202120212021
Автор методаKaiming HeZe LiuDosovitskiy, A. et al.
ТипNeural network architectureNeural network architectureTransformer architecture for images (self-attention over patches)
Основополагающий источникHe, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022). DOI ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
Другие названияMAE, Vision MAESwin, Hierarchical Vision TransformerGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Связанные445
СводкаMasked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.The Swin Transformer is a hierarchical vision transformer introduced by Liu et al. in 2021 that uses shifted window attention to achieve computational efficiency while maintaining strong performance on computer vision tasks. Unlike the original Vision Transformer which applies global self-attention, Swin uses local window-based attention with periodic shifting to balance expressiveness and efficiency.The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).
ScholarGateНабор данных
  1. v1
  2. 1 Источники
  3. PUBLISHED
  1. v1
  2. 1 Источники
  3. PUBLISHED
  1. v1
  2. 2 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Masked Autoencoders · Swin Transformer · Vision Transformer. Получено 2026-06-19 из https://scholargate.app/ru/compare